Add Streamlit app for CVD prediction

app.py

@@ -0,0 +1,124 @@
+import streamlit as st
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import re
+from pydub import AudioSegment
+import speech_recognition as sr
+import io
+
+# Load model and tokenizer from local fine-tuned directory
+MODEL_PATH = "Tufan1/BioMedLM-Cardio-Fold2"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = AutoModelForCausalLM.from_pretrained(MODEL_PATH)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+# Dictionaries to decode user inputs
+gender_map = {1: "Female", 2: "Male"}
+cholesterol_map = {1: "Normal", 2: "High", 3: "Extreme"}
+glucose_map = {1: "Normal", 2: "High", 3: "Extreme"}
+binary_map = {0: "No", 1: "Yes"}
+
+# Function to predict diagnosis using the LLM
+def get_prediction(age, gender, height, weight, ap_hi, ap_lo,
+                   cholesterol, glucose, smoke, alco, active):
+    input_text = f"""Patient Record:
+- Age: {age} years
+- Gender: {gender_map[gender]}
+- Height: {height} cm
+- Weight: {weight} kg
+- Systolic BP: {ap_hi} mmHg
+- Diastolic BP: {ap_lo} mmHg
+- Cholesterol Level: {cholesterol_map[cholesterol]}
+- Glucose Level: {glucose_map[glucose]}
+- Smokes: {binary_map[smoke]}
+- Alcohol Intake: {binary_map[alco]}
+- Physically Active: {binary_map[active]}
+
+Diagnosis:"""
+
+    inputs = tokenizer(input_text, return_tensors="pt").to(device)
+    model.eval()
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=4)
+    decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    diagnosis = decoded.split("Diagnosis:")[-1].strip()
+    return diagnosis
+
+# Function to extract patient features from a phrase or transcribed audio
+def extract_details_from_text(text):
+    age = int(re.search(r'(\d+)\s*year', text).group(1)) if re.search(r'(\d+)\s*year', text) else None
+    gender = 2 if "man" in text.lower() else (1 if "female" in text.lower() else None)
+    height = int(re.search(r'(\d+)\s*cm', text).group(1)) if re.search(r'(\d+)\s*cm', text) else None
+    weight = int(re.search(r'(\d+)\s*kg', text).group(1)) if re.search(r'(\d+)\s*kg', text) else None
+    bp_match = re.search(r'BP\s*(\d+)[/](\d+)', text)
+    ap_hi, ap_lo = (int(bp_match.group(1)), int(bp_match.group(2))) if bp_match else (None, None)
+    cholesterol = 3 if "peak" in text.lower() else 2 if "elevated" in text.lower() else 1
+    glucose = 3 if "extreme" in text.lower() else 2 if "high" in text.lower() else 1
+    smoke = 1 if "smoke" in text.lower() else 0
+    alco = 1 if "alcohol" in text.lower() else 0
+    active = 1 if "exercise" in text.lower() or "active" in text.lower() else 0
+    return age, gender, height, weight, ap_hi, ap_lo, cholesterol, glucose, smoke, alco, active
+
+# Streamlit UI
+st.set_page_config(page_title="Cardiovascular Disease Predictor", layout="centered")
+st.title("🫀 Cardiovascular Disease Predictor (LLM Powered)")
+st.markdown("This tool uses a fine-tuned BioMedLM model to predict cardiovascular conditions from structured, text, or voice input.")
+
+input_mode = st.radio("Choose input method:", ["Manual Input", "Text Phrase", "Audio Upload"])
+
+if input_mode == "Manual Input":
+    age = st.number_input("Age (years)", min_value=1, max_value=120)
+    gender = st.selectbox("Gender", [("Female", 1), ("Male", 2)], format_func=lambda x: x[0])[1]
+    height = st.number_input("Height (cm)", min_value=50, max_value=250)
+    weight = st.number_input("Weight (kg)", min_value=10, max_value=200)
+    ap_hi = st.number_input("Systolic BP", min_value=80, max_value=250)
+    ap_lo = st.number_input("Diastolic BP", min_value=40, max_value=150)
+    cholesterol = st.selectbox("Cholesterol", [("Normal", 1), ("High", 2), ("Extreme", 3)], format_func=lambda x: x[0])[1]
+    glucose = st.selectbox("Glucose", [("Normal", 1), ("High", 2), ("Extreme", 3)], format_func=lambda x: x[0])[1]
+    smoke = st.radio("Smoker?", [("No", 0), ("Yes", 1)], format_func=lambda x: x[0])[1]
+    alco = st.radio("Alcohol Intake?", [("No", 0), ("Yes", 1)], format_func=lambda x: x[0])[1]
+    active = st.radio("Physically Active?", [("No", 0), ("Yes", 1)], format_func=lambda x: x[0])[1]
+
+    if st.button("Predict Diagnosis"):
+        diagnosis = get_prediction(age, gender, height, weight, ap_hi, ap_lo,
+                                   cholesterol, glucose, smoke, alco, active)
+        st.success(f"🩺 **Predicted Diagnosis:** {diagnosis}")
+
+elif input_mode == "Text Phrase":
+    phrase = st.text_area("Enter patient details in natural language:", height=200)
+    if st.button("Extract & Predict"):
+        try:
+            values = extract_details_from_text(phrase)
+            if all(v is not None for v in values):
+                diagnosis = get_prediction(*values)
+                st.success(f"🩺 **Predicted Diagnosis:** {diagnosis}")
+            else:
+                st.warning("Couldn't extract all fields from the text. Please revise.")
+        except Exception as e:
+            st.error(f"Error: {e}")
+
+elif input_mode == "Audio Upload":
+    uploaded_file = st.file_uploader("Upload audio file (WAV, MP3, M4A)", type=["wav", "mp3", "m4a"])
+    if uploaded_file:
+        st.audio(uploaded_file, format='audio/wav')
+        audio = AudioSegment.from_file(uploaded_file)
+        wav_io = io.BytesIO()
+        audio.export(wav_io, format="wav")
+        wav_io.seek(0)
+
+        recognizer = sr.Recognizer()
+        with sr.AudioFile(wav_io) as source:
+            audio_data = recognizer.record(source)
+
+        try:
+            text = recognizer.recognize_google(audio_data)
+            st.markdown(f"**Transcribed Text:** _{text}_")
+            values = extract_details_from_text(text)
+            if all(v is not None for v in values):
+                diagnosis = get_prediction(*values)
+                st.success(f"🩺 **Predicted Diagnosis:** {diagnosis}")
+            else:
+                st.warning("Could not extract complete information from audio.")
+        except Exception as e:
+            st.error(f"Audio processing error: {e}")

requirements.txt

@@ -0,0 +1,348 @@
+eabsl-py==2.1.0
+accelerate==1.6.0
+addict==2.4.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.14
+aiosignal==1.3.2
+aliyun-python-sdk-core==2.16.0
+aliyun-python-sdk-kms==2.16.5
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.4.0
+apturl==0.5.2
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asttokens==2.4.1
+astunparse==1.6.3
+async-lru==2.0.4
+async-timeout==5.0.1
+attrs==24.2.0
+babel==2.16.0
+bcrypt==3.2.0
+beautifulsoup4==4.12.3
+bitsandbytes==0.45.5
+black==24.2.0
+bleach==6.1.0
+blinker==1.9.0
+boto3==1.36.25
+botocore==1.36.25
+Brlapi==0.8.3
+cachetools==5.5.2
+certifi==2020.6.20
+cffi==1.17.1
+chardet==4.0.0
+charset-normalizer==3.4.1
+chumpy==0.70
+click==8.1.8
+colorama==0.4.4
+comm==0.2.0
+command-not-found==0.3
+contourpy==1.3.0
+crcmod==1.7
+cryptography==3.4.8
+cupshelpers==1.0
+cycler==0.12.1
+Cython==3.0.11
+datasets==3.4.1
+dbus-python==1.2.18
+debugpy==1.8.0
+decorator==5.2.1
+deepface==0.0.93
+defer==1.0.6
+defusedxml==0.7.1
+depthai==2.23.0.0
+dill==0.3.8
+distlib==0.3.6
+distro==1.7.0
+distro-info==1.1+ubuntu0.2
+docker-pycreds==0.4.0
+duplicity==0.8.21
+exceptiongroup==1.2.0
+executing==2.0.1
+fasteners==0.14.1
+fastjsonschema==2.20.0
+filelock==3.14.0
+fire==0.7.0
+Flask==3.1.0
+flask-cors==5.0.1
+flatbuffers==25.2.10
+fonttools==4.53.1
+fqdn==1.5.1
+frozenlist==1.5.0
+fsspec==2023.9.2
+future==0.18.2
+gast==0.4.0
+gdown==5.2.0
+gitdb==4.0.11
+GitPython==3.1.43
+google-auth==2.38.0
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+greenlet==1.1.2
+grpcio==1.70.0
+gunicorn==23.0.0
+gyp==0.1
+h11==0.14.0
+h5py==3.13.0
+httpcore==1.0.5
+httplib2==0.20.2
+httpx==0.27.2
+huggingface-hub==0.30.1
+hydra-core==1.3.2
+idna==3.3
+importlib-metadata==4.6.4
+install==1.3.5
+iopath==0.1.10
+ipykernel==6.27.1
+ipython==8.18.1
+ipywidgets==8.1.5
+isoduration==20.11.0
+itsdangerous==2.2.0
+jedi==0.19.1
+jeepney==0.7.1
+Jinja2==3.1.2
+jmespath==0.10.0
+joblib==1.4.2
+json-tricks==3.17.3
+json5==0.9.25
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+jupyter==1.1.1
+jupyter-console==6.6.3
+jupyter-events==0.10.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.0
+jupyter_core==5.5.1
+jupyter_server==2.14.2
+jupyter_server_terminals==0.5.3
+jupyterlab==4.2.5
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.13
+kaggle==1.7.4.2
+keras==2.11.0
+Keras-Preprocessing==1.1.2
+keyring==23.5.0
+kiwisolver==1.4.7
+language-selector==0.1
+largestinteriorrectangle==0.2.1
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+libclang==18.1.1
+libcst==1.4.0
+llvmlite==0.44.0
+lockfile==0.12.2
+louis==3.20.0
+lz4==4.4.4
+macaroonbakery==1.3.1
+Mako==1.1.3
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.9.2
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+mistune==3.0.2
+ml_dtypes==0.5.1
+mmdet==3.0.0
+mmengine==0.7.4
+model-index==0.1.11
+monotonic==1.6
+more-itertools==8.10.0
+moreorless==0.4.0
+mpmath==1.3.0
+msgpack==1.0.3
+mtcnn==1.0.0
+multidict==6.2.0
+multiprocess==0.70.16
+munkres==1.1.4
+mypy-extensions==1.0.0
+namex==0.0.8
+natsort==8.4.0
+nbclient==0.10.0
+nbconvert==7.16.4
+nbformat==5.10.4
+nest-asyncio==1.5.8
+netifaces==0.11.0
+networkx==3.1
+notebook==7.2.2
+notebook_shim==0.2.4
+numba==0.61.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cusparselt-cu12==0.6.2
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
+oauthlib==3.2.0
+olefile==0.46
+omegaconf==2.3.0
+opencv-python==4.10.0.84
+opencv-python-headless==4.10.0.84
+opendatalab==0.0.10
+openmim==0.3.9
+openxlab==0.1.2
+opt_einsum==3.4.0
+optree==0.14.0
+ordered-set==4.1.0
+oss2==2.17.0
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.2
+pandocfilters==1.5.1
+paramiko==2.9.3
+parso==0.8.3
+pathspec==0.12.1
+peft==0.15.1
+pexpect==4.8.0
+pillow==10.4.0
+pipreq==0.4
+platformdirs==3.5.1
+portalocker==2.10.1
+prometheus_client==0.20.0
+prompt-toolkit==3.0.43
+propcache==0.3.0
+protobuf==3.12.4
+psutil==5.9.5
+ptyprocess==0.7.0
+pure-eval==0.2.2
+py-cpuinfo==9.0.0
+pyarrow==19.0.1
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycairo==1.20.1
+pycocotools==2.0.8
+pycparser==2.22
+pycryptodome==3.21.0
+pycups==2.0.1
+pydantic==2.11.1
+pydantic_core==2.33.0
+pydub==0.25.1
+Pygments==2.17.2
+PyGObject==3.42.1
+PyJWT==2.3.0
+pymacaroons==0.13.0
+PyNaCl==1.5.0
+pynvim==0.4.2
+pyparsing==2.4.7
+PyPDF2==3.0.1
+pyRFC3339==1.1
+pysmbc==1.0.23
+PySocks==1.7.1
+python-apt==2.4.0+ubuntu4
+python-dateutil==2.8.2
+python-debian==0.1.43+ubuntu1.1
+python-json-logger==2.0.7
+python-slugify==8.0.4
+python-version==0.0.2
+pytz==2023.4
+pyxdg==0.27
+PyYAML==6.0.2
+pyzmq==25.1.2
+referencing==0.35.1
+regex==2024.11.6
+reportlab==3.6.8
+requests==2.32.3
+requests-oauthlib==2.0.0
+retina-face==0.0.17
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.4.2
+rpds-py==0.20.0
+rsa==4.9
+s3transfer==0.11.2
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.11.3
+seaborn==0.13.0
+SecretStorage==3.3.1
+Send2Trash==1.8.3
+sentry-sdk==2.25.1
+setproctitle==1.3.5
+shapely==2.0.7
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+soupsieve==2.6
+SpeechRecognition==3.14.2
+ssh-import-id==5.11
+stack-data==0.6.3
+stdlibs==2024.5.15
+stitching==0.6.1
+supervision==0.23.0
+sympy==1.13.1
+systemd-python==234
+tabulate==0.9.0
+tensorboard==2.11.2
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.11.0
+tensorflow-estimator==2.11.0
+tensorflow-io-gcs-filesystem==0.37.1
+termcolor==2.5.0
+terminado==0.18.1
+terminaltables==3.1.10
+text-unidecode==1.3
+tf-keras==2.15.0
+thop==0.1.1.post2209072238
+threadpoolctl==3.6.0
+tiktoken==0.9.0
+timm==1.0.14
+tinycss2==1.3.0
+tokenizers==0.21.1
+toml==0.10.2
+tomli==2.0.1
+tomlkit==0.13.2
+torch==2.6.0
+torchvision==0.21.0
+tornado==6.4
+tqdm==4.67.1
+trailrunner==1.4.0
+traitlets==5.14.0
+transformers==4.51.0
+triton==3.2.0
+types-python-dateutil==2.9.0.20240906
+typing-inspection==0.4.0
+typing_extensions==4.13.1
+tzdata==2023.3
+ubuntu-drivers-common==0.0.0
+ubuntu-pro-client==8001
+ufmt==2.0.0b2
+ufw==0.36.1
+ultralytics==8.2.100
+ultralytics-thop==2.0.8
+unattended-upgrades==0.1
+uri-template==1.3.0
+urllib3==2.3.0
+usb-creator==0.3.7
+usort==1.0.2
+virtualenv==20.23.0
+wadllib==1.3.6
+wandb==0.19.9
+warmup-scheduler==0.3
+wcwidth==0.2.12
+webcolors==24.8.0
+webencodings==0.5.1
+websocket-client==1.8.0
+Werkzeug==3.1.3
+widgetsnbextension==4.0.13
+wrapt==1.14.1
+xdg==5
+xkit==0.0.0
+xtcocotools==1.14.3
+xxhash==3.5.0
+yacs==0.1.8
+yapf==0.43.0
+yarl==1.18.3
+zipp==1.0.0